File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Dynamic virtual machine management via approximate Markov decision process

TitleDynamic virtual machine management via approximate Markov decision process
Authors
Issue Date2016
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000359
Citation
The 35th Annual IEEE International Conference on Computer Communications (IEEE INFOCOM 2016), San Francisco, CA., 10-14 April 2016. In Conference Proceedings, 2016 How to Cite?
AbstractEfficient virtual machine (VM) management can dramatically reduce energy consumption in data centers. Existing VM management algorithms fall into two categories based on whether the VMs' resource demands are assumed to be static or dynamic. The former category fails to maximize the resource utilization as they cannot adapt to the dynamic nature of VMs' resource demands. Most approaches in the latter category are heuristical and lack theoretical performance guarantees. In this work, we formulate dynamic VM management as a large-scale Markov Decision Process (MDP) problem and derive an optimal solution. Our analysis of real-world data traces supports our choice of the modeling approach. However, solving the large-scale MDP problem suffers from the curse of dimensionality. Therefore, we further exploit the special structure of the problem and propose an approximate MDP-based dynamic VM management method, called MadVM. We prove the convergence of MadVM and analyze the bound of its approximation error. Moreover, MadVM can be implemented in a distributed system, which should suit the needs of real data centers. Extensive simulations based on two real-world workload traces show that MadVM achieves significant performance gains over two existing baseline approaches in power consumption, resource shortage and the number of VM migrations. Specifically, the more intensely the resource demands fluctuate, the more MadVM outperforms. © 2016 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/234130
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorHan, Z-
dc.contributor.authorTan, H-
dc.contributor.authorChen, G-
dc.contributor.authorWang, R-
dc.contributor.authorChen, Y-
dc.contributor.authorLau, FCM-
dc.date.accessioned2016-10-14T06:59:14Z-
dc.date.available2016-10-14T06:59:14Z-
dc.date.issued2016-
dc.identifier.citationThe 35th Annual IEEE International Conference on Computer Communications (IEEE INFOCOM 2016), San Francisco, CA., 10-14 April 2016. In Conference Proceedings, 2016-
dc.identifier.isbn978-146739953-1-
dc.identifier.issn0743-166X-
dc.identifier.urihttp://hdl.handle.net/10722/234130-
dc.description.abstractEfficient virtual machine (VM) management can dramatically reduce energy consumption in data centers. Existing VM management algorithms fall into two categories based on whether the VMs' resource demands are assumed to be static or dynamic. The former category fails to maximize the resource utilization as they cannot adapt to the dynamic nature of VMs' resource demands. Most approaches in the latter category are heuristical and lack theoretical performance guarantees. In this work, we formulate dynamic VM management as a large-scale Markov Decision Process (MDP) problem and derive an optimal solution. Our analysis of real-world data traces supports our choice of the modeling approach. However, solving the large-scale MDP problem suffers from the curse of dimensionality. Therefore, we further exploit the special structure of the problem and propose an approximate MDP-based dynamic VM management method, called MadVM. We prove the convergence of MadVM and analyze the bound of its approximation error. Moreover, MadVM can be implemented in a distributed system, which should suit the needs of real data centers. Extensive simulations based on two real-world workload traces show that MadVM achieves significant performance gains over two existing baseline approaches in power consumption, resource shortage and the number of VM migrations. Specifically, the more intensely the resource demands fluctuate, the more MadVM outperforms. © 2016 IEEE.-
dc.languageeng-
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000359-
dc.relation.ispartofIEEE Infocom Proceedings-
dc.rightsIEEE Infocom Proceedings. Copyright © IEEE Computer Society.-
dc.rights©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.titleDynamic virtual machine management via approximate Markov decision process-
dc.typeConference_Paper-
dc.identifier.emailLau, FCM: fcmlau@cs.hku.hk-
dc.identifier.authorityLau, FCM=rp00221-
dc.description.natureLink_to_subscribed_fulltext-
dc.identifier.doi10.1109/INFOCOM.2016.7524384-
dc.identifier.scopuseid_2-s2.0-84983261312-
dc.identifier.hkuros267343-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 161102-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats